Tag Archives: machine learning

One Algorithm To Learn Anything [An Interview with Pedro Domingos, Author of The Master Algorithm]

Releasing today (Sept. 22, 2015) is the fantastic new book, The Master Algorithm, by machine learning expert and University of Washington Computer Science Professor, Pedro Domingos. Recently, I got the opportunity to visit with Dr. Domingos about his new book and machine learning in general. See below for his fears of machine learning, thoughts on education, and tips for learning data science.

Stay tuned later this week for a complete review of the book!

The Master Algorithm book
The Master Algorithm book
Why This Book and Why Now?

Dr. Domingos explains the 2 primary reasons why the topic and timing are just perfect for the book.

  1. Real Need – Currently, machine learning is a topic of interest in society. Machine learning and data science are being discussed in news and politics. The one downfall, most people don’t really understand the topic. He does fault machine learning experts for not making the topic understandable to a broader audience. Many of the concepts from machine learning can be explained without complex mathematics formulas. The new book aims to do just that while exposing the topic of machine learning to others.
  2. Unity – Dr. Domingos explains the five camps of machine learning: symbolists, connectionists, evolutionaries, bayesians, and analogizers. He thinks right now is the time to start thinking and working toward combining the camps to form a single general purpose learner. More on those camps can be discovered in the book.

What are the limits of the Master Algorithm?

Not many! Dr. Domingos does not think the algorithm will perform magic, but he did state,

“It should truly be able to learn anything given the requisite data.”

The trick will be compiling the “requisite data”.

What are the biggest fears of the Master Algorithm?

As is emphasized numerous times in the book, Dr. Domingos does not envision The Master Algorithm creating bots that will eventually take over the world. No, the real problem is already a concern with machine learning.

Computers are making decisions for humans every day, and sometimes those decisions are wrong.

Also, he thinks machine learning will discover and expose things we do not like about ourselves. Then he envisions some challenges with ownership of that data and the algorithmic results.

How soon will we see the Master Algorithm?

Dr. Domingos is not sure if the algorithm will be discovered tomorrow, not for many years, or ever. He does think the next five years will see some combining of the best parts of the five camps.

What are some problems in the application of machine learning?

He is currently seeing a problem in the practice of applying machine learning. He sees companies take the latest research, which is a good thing, and turn it into a large engineering project. Eventually, those projects hit a wall of being too complex. That is why he thinks companies are going to start combining and refining machine learning projects to make them less complex and more maintainable.

What advice would you give to high school students or undergrads about pursuing machine learning/data science?

Dr. Domingos believes they (high school and undergraduate students) are the primary audience for the book. He did expand on the answer and provide a nice todo list for people getting into the field of data science and machine learning.

  1. Read The Master Algorithm
  2. Explore further readings – the end of the book contains details on further readings for each chapter
  3. Take an online course (MOOC) – many good choices
  4. Start implementing some algorithms – either on your own projects or in a competition such as Kaggle, this will help you identify some of the common pitfalls

How do you see machine learning affecting education?

He sees two clear ways in which machine learning will have an impact on education.

  1. Machine learning is something people in every field will need to know. It is becoming the new toolkit.
  2. Machine learning is going to personalize education. MOOCs are already starting to do this, but the future shows much more promise in this specific area.

Do you ever have plans to offer the Coursera Machine Learning course in a live format?

Luckily for us learners, Dr. Domingos does plan to offer the course in a live format. He always intended the course to happen that way, but some unexpected things arose, and the class never ran live. It doesn’t have a scheduled date yet, but the details will be posted on this blog when it does happen. In the mean time, all the lectures are available on the Cousera class page.

Finally, do you have a unique use of machine learning in your own life?

Dr. Domingos and few other professors at the University of Washington are in the initial steps of a project named eProf, for electronic Professor. The goal is to automate some of the responsibilities of a professor. The project is still in the discussion stages, but he thinks it would make a useful open source project. Hopefully, more to come on eProf in the future!

Remember, check back later this week for a complete review of the book!

Yinyang K-Means: A Drop-In Replacement of the Classic K-Means

This week; Yufei Ding, Yue Zhao, Xipeng Shen, Madanlal Musuvathi, and Todd Mytkowicz will be presenting Yinyang K-means at the 2015 International Conference on Machine Learning.

The algorithm guarantees the same results as traditional K-means, but it produces results with an order of magnitude higher performance.

An abstract of the paper and a PDF download can be accessed at Yinyang K-Means: A Drop-In Replacement of the Classic K-Means with Consistent Speedup.

Machine Learning to Play Super Mario

A fun video to watch. Very Impressive!

The technique uses a genetic algorithm to training a neural network. A paper with more details can be found at, Evolving Neural Networks through Augmenting Topologies (NEAT)

Model-based Machine Learning, Free Early Access Book

Model-based Machine Learning, Free Early Access Book

Free Deep Learning Book

Yoshua Bengio, Ian Goodfellow and Aaron Courville are writing a deep learning book for MIT Press. The book is not yet complete, but the drafts of the chapters are all available online. The authors are also collecting comments about the chapters before the book goes to press.

The book is broken into 3 sections:

  1. Math and Machine Learning Fundamentals
  2. Modern Deep Neural Networks
  3. Current Research in Deep Learning

The book is very technical and probably suitable for a graduate level course. However, if you have the time and interest, resources such as this are highly valuable.

Next.ML Machine Learning Conference

If you are based near San Francisco and interested in machine learning, the Next.ML conference is going on this weekend, January 17, 2015. The conference is a bunch of workshops covering the latest trends in:

  • DEEP LEARNING
  • PROBABILISTIC PROGRAMMING
  • PARALLEL┬áLEARNING
  • JULIA
  • OTHER MACHINE LEARNING TOPICS AND TOOLS

The lineup of speakers is great, coming from places like MIT, Facebook, Stanford, Domino Data Labs, and others. Bring your laptop because all participants will leave the conference with lots of great software and datasets.

Note: If you would like to attend the conference, you can use the coupon code “media” to save 30% off the conference admission.

CMU Machine Learning Summer School Videos

It was a 2-week intensive course focused on machine learning for big data. Some of the top academics in machine learning gave presentations. Most of the videos are fairly long (around 1 hour each), but a whole lot of material is covered.

All the CMU Machine Learning Summer School Videos are on Youtube.

Here is one lecture by Alex Smola on Scalable Machine Learning.

Huge List of Big Data and Machine Learning Technologies

Onur Akpolat has put together A curated list of awesome big data frameworks and resources. The list is very extensive and includes: NoSQL databases, machine learning libraries, frameworks, filesystems and more.

On a similar note, Joseph Misiti has compiled a large list of machine learning specific resources. The list is titled, Awesome Machine Learning, and it includes resources for various languages, NLP, visualization, and more.

Both lists are on Github, so if you notice something missing from the list, feel free to add it. Contributions are welcome.

Coursera Machine Learning Starts (Again) Today

The excellent and popular Machine Learning class from Coursera and Andrew Ng starts today. This is the 3rd or 4th run of the course.

Machine Learning MOOC from EdX

EdX, a MOOC site, is offering Learning From Data. This is a course about machine learning offered by Caltech. The course started yesterday, so there is still time to get started. The course has 2 tracks: audit and certificate. It looks great. Good Luck.